Skip to main content
Glama

Xearno Tools

Hong Kong (HK) Salaries Tax Calculator 2026/27

income_tax_hong_kong
Read-only

What your Hong Kong salary actually costs you in tax this year, after allowances — and whether the standard rate caps the bill. Hong Kong does not tax salaries with a bracket table. It runs two calculations and charges you the lower one: progressive rates of 2% to 17% on what remains after your allowances, or a flat standard rate on your income before any allowances at all — 15% on the first HK$5,000,000, 16% above it. Which one wins turns entirely on your allowances, so a married taxpayer with children crosses over at a far higher salary than someone single. Most calculators model only the progressive scale, and so does most AI, which is why both overstate the bill for higher earners, sometimes by a lot. This runs both, shows you which one binds and by how much, and takes off the year’s one-off reduction at the end.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mpfNoMPF mandatory contributions (HK$) Deductible up to HK$18,000 a year. Employee mandatory contributions only — voluntary ones are not deductible under this cap.
yearNoYear of assessment Allowances rose in 2026/27 (basic HK$132,000 → HK$145,000). The one-off reduction for 2026/27 has not been announced yet, so it is treated as zero until the February 2027 Budget.2026/27
incomeNoAnnual income (HK$) Total assessable income for the year — salary, bonus, commission, and the rental value of any employer-provided housing.
statusNoAssessment basis The decisive input. Joint assessment doubles the basic allowance, which raises the income at which the standard rate takes over — the crossover is net income above 8.5 × allowances + HK$900,000.single
parentsNoDependent parents/grandparents aged 60+ HK$55,000 each for 2026/27 (HK$50,000 for 2025/26). The 55–59 band is half and is not modelled here.
childrenNoChildren claimed HK$140,000 each for 2026/27 (HK$130,000 for 2025/26), for up to nine children. The extra year-of-birth allowance is not modelled.
otherDeductionsNoOther deductions (HK$) Self-education (max 100,000), home-loan interest (100,000, or 120,000 with a young child), domestic rent (same), elderly residential care, annuity/TVC (60,000), VHIS. Enter the total.
parentsLiveWithNoDo those parents live with you? Living with you the whole year doubles the dependent-parent allowance. Easy to miss, and worth HK$55,000 of allowance per parent in 2026/27.no

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, and the description adds substantial context: it explains the two calculations, the lower-bill rule, the allowance-dependent crossover, and the treatment of the one-off reduction. This goes well beyond the annotation and helps the agent understand how results are computed, though it does not detail the return format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place: it explains the HK tax system, why mainstream calculators fail, and what the tool outputs. It is well-structured and front-loaded with purpose, though slightly verbose for a simple calculator.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a fully documented schema and readOnlyHint annotation, the description covers the tool's logic and key outputs (which method binds, the reduction). It does not specify the exact return object, but for a read-only calculator the explanation is adequate given the complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage, with each parameter described in detail (caps, exclusions, year-specific values). The tool description itself adds little parameter-specific detail, so the baseline of 3 applies; the schema carries the heavy lifting for parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states this is a Hong Kong salaries tax calculator, with a specific verb ('costs you') and resource ('your Hong Kong salary'). It distinguishes itself from siblings by emphasizing the unique dual-calculation method (progressive rates vs. standard rate cap), which sets it apart from generic income tax tools or other jurisdictions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool — for accurate HK salaries tax, especially for higher earners where the standard rate may bind — and contrasts it with other calculators that only model the progressive scale. It does not explicitly name alternative tools or list exclusions, so it is clear but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation4/5

Each tool targets a distinct niche (e.g., specific country tax rules, loan types, or legal calculations), with detailed descriptions that clarify boundaries. However, the large number of tools (66) could cause some confusion for an agent trying to select the right one for a general query, especially when multiple tools relate to the same country.

Naming Consistency4/5

Tool names follow a mostly predictable pattern: lowercase words separated by underscores, often starting with a country name (e.g., 'uk_stamp_duty_sdlt') or a topic (e.g., 'compound_growth'). There are minor deviations, such as abbreviations ('npv_irr', 'sip') and varying use of verbs, but overall the naming is clear and consistent.

Tool Count3/5

At 66 tools, the server is unusually large and covers an extensive range of financial and legal calculators. While each tool justifies its existence, the count exceeds the typical well-scoped range (3–15), making the server feel bloated. A more modular design might improve coherence.

Completeness4/5

The tool set covers a wide array of domains: personal income taxes, property taxes, loan calculations, investment returns, and specific country regulations. Minor gaps exist (e.g., missing tools for corporate taxes, general retirement planning, or insurance), but the overall coverage is thorough and addresses many niche scenarios that general AI handles poorly.

Resources